Events

This workshop offers a complete introduction to image processing and deep learning for computer vision. Digital image processing begins with understanding color spaces, which help interpret and manipulate visual information while enabling creative drawing and annotations through OpenCV. Transformational techniques like filters, gradients, and edge detection further enhance images by reducing noise, highlighting details, and identifying object boundaries using methods. Building on these foundations, computer vision systems detect meaningful features, from simple corners and edges using algorithms like Harris and SIFT to complex tasks like face detection and recognition using Haar Cascades and deep learning models. Advancing into modern multimedia, Generative AI integrates text-to-speech (TTS) and lip-sync technologies to create realistic talking videos, aligning synthesized speech with facial movements using tools like Wav2Lip and TTS models, ultimately connecting low-level image processing with high-level AI-driven content creation. Participants will also gain hands-on experience with Python programming for computer vision and learn to implement advanced models for real-time applications. By the end, attendees will be equipped with both theoretical knowledge and practical skills to apply modern vision techniques to real-world problems.